• Journal of Drive and Control
• /
• v.19 no.4
• /
• pp.104-109
• /
• 2022

For autonomous driving research using AI, datasets collected from road environments play an important role. In other countries, various datasets such as CityScapes, A2D2, and BDD have already been released, but datasets suitable for the domestic road environment still need to be provided. This paper analyzed and verified the dataset reflecting the Korean driving environment. In order to verify the training dataset, the class imbalance was confirmed by comparing the number of pixels and instances of the dataset. A similar A2D2 dataset was trained with the same deep learning model, ConvNeXt, to compare and verify the constructed dataset. IoU was compared for the same class between two datasets with ConvNeXt and mIoU was compared. In this paper, it was confirmed that the collected dataset reflecting the driving environment of Korea is suitable for learning.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.406-412
• /
• 2022

Scene classification of very high-resolution (VHR) imagery can attribute semantics to land cover in a variety of domains. Real-world application requirements have not been addressed by conventional techniques for remote sensing image classification. Recent research has demonstrated that deep convolutional neural networks (CNNs) are effective at extracting features due to their strong feature extraction capabilities. In order to improve classification performance, these approaches rely primarily on semantic information. Since the abstract and global semantic information makes it difficult for the network to correctly classify scene images with similar structures and high interclass similarity, it achieves a low classification accuracy. We propose a VHR remote sensing image classification model that uses extracts the global feature from the original VHR image using an EfficientNet-V2L CNN pre-trained to detect similar classes. The image is then classified using a multilayer perceptron (MLP). This method was evaluated using two benchmark remote sensing datasets: the 21-class UC Merced, and the 38-class PatternNet. As compared to other state-of-the-art models, the proposed model significantly improves performance.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.94-98
• /
• 2018

We propose Wide Inception ResNet (WIR Net) an optimized neural network architecture as a real-time semantic segmentation method for autonomous driving. The neural network architecture consists of an encoder that extracts features by applying a residual connection and inception module, and a decoder that increases the resolution by using transposed convolution and a low layer feature map. We also improved the performance by applying an ELU activation function and optimized the neural network by reducing the number of layers and increasing the number of filters. The performance evaluations used an NVIDIA Geforce GTX 1080 and TX1 boards to assess the class and category IoU for cityscapes data in the driving environment. The experimental results show that the accuracy of class IoU 53.4, category IoU 81.8 and the execution speed of $640{\times}360$, $720{\times}480$ resolution image processing 17.8fps and 13.0fps on TX1 board.

• The KIPS Transactions:PartD
• /
• v.12D no.1 s.97
• /
• pp.165-178
• /
• 2005

A product classification scheme is the foundation on which product databases are designed, and plays a central role in almost all aspects of management and use of product information. It needs to meet diverse user views to support efficient and convenient use of product information. It needs to be changed and evolved very often without breaking consistency in the cases of introduction of new products, extinction of existing products, class reorganization, and class specialization. It also needs to be merged and mapped with other classification schemes without information loss when B2B transactions occur. For these requirements, a classification scheme should be so dynamic that it takes in them within right time and cost. The existing classification schemes widely used today such as UNSPSC and eCl@ss, however, have a lot of limitations to meet these requirements for dynamic features of classification. Product information implies a plenty of semantics such as class attributes like material, time, place, etc., and integrity constraints. In this Paper, we analyze the dynamic features of product databases and the limitation of existing code based classification schemes, and describe the semantic classification model proposed in [1], which satisfies the requirements for dynamic features of product databases. It provides a means to explicitly and formally express more semantics for product classes and organizes class relationships into a graph.

• Journal of Korean Library and Information Science Society
• /
• v.37 no.2
• /
• pp.191-216
• /
• 2006

This paper deals with the definition, function and type of ontology based on precedent study particularly the paper describes a Using Methods for OWL vocabulary and syntactics to Ontology Automatic Construction. Also for easily learning the usage methods for OWL vocabulary and syntactics, it introduces a detailed definition for syntactics of Class, Property, Class relativeness, Property relativeness and presents a sample data and explanation based on Wine Ontology which have constructed.

• Journal of Korean Elementary Science Education
• /
• v.40 no.3
• /
• pp.311-325
• /
• 2021

Modern society demands a new science teacher image. Compared to other school ages, elementary school students are the time when the teacher's influence plays a large role and is the time when they first encounter science subjects. The role of science teachers is very important as the starting point for the initial image of science learning and attitudes toward science by elementary science teachers. Therefore, it is very important to correctly establish an image of an elementary science teacher. The purpose of this study is to analyze the images of science teachers that elementary school students prefer and avoid according to their class situation. To this end, 534 elementary school students were divided into five classes: class type, class material presentation method, subject instruction method, subject content explanation method, and class atmosphere, and the image of science teacher who prefers and avoids is described in an open format. Concepts presented by elementary school students were analyzed using Semantic network analysis. The conclusions of this study are as follows. First, the image of a science teacher preferred or avoided by elementary school students was determined according to how the science teacher did the class. Second, elementary school students prefer activity-oriented classes such as experimental classes, and there is a need for classes to be conducted in this manner. Lastly, small changes and efforts of teachers in teaching methods are needed so that changes to science classes preferred by elementary school students can be achieved.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.18 no.1
• /
• pp.135-147
• /
• 2016

The purpose of this research is to study the semantic characteristics of outdoor brand names by analyzing 94 brand names in domestic market, so as to propose ways to develop strategic brand names. The results are as follows. When it comes to outdoor brand products, the emphasis is placed on their functional features. Thus, the majority of outdoor brands surveyed in this Study were using strategic descriptive brand names which clearly denote the properties and effects of the relevant products to leave lasting impressions on consumers'minds. In other words, the outdoor brands surveyed herein were using brands which inform consumers of the specific business and product categories, express the concept of the brands, and provide them with information on the features and benefits of the products such as high quality, high-class, and luxurious lifestyle. In conclusion, the components of outdoor brand names are crucial elements which symbolize the concepts, functions or features of the relevant brands. In order to develop brand names consisting of components which build brand powers and enhance brand images, it is imparetive to develop more unique and characteristic brand names.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.392-412
• /
• 2018

Due to the semantic gap problem across different modalities, automatically retrieval from multimedia information still faces a main challenge. It is desirable to provide an effective joint model to bridge the gap and organize the relationships between them. In this work, we develop a deep image annotation and classification by fusing multi-modal semantic topics (DAC_mmst) model, which has the capacity for finding visual and non-visual topics by jointly modeling the image and loosely related text for deep image annotation while simultaneously learning and predicting the class label. More specifically, DAC_mmst depends on a non-parametric Bayesian model for estimating the best number of visual topics that can perfectly explain the image. To evaluate the effectiveness of our proposed algorithm, we collect a real-world dataset to conduct various experiments. The experimental results show our proposed DAC_mmst performs favorably in perplexity, image annotation and classification accuracy, comparing to several state-of-the-art methods.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.6
• /
• pp.33-44
• /
• 2005

This study lets you know how semantic network programs called mind tools have an effect on students' learning achievements and learning motives regarded students' cognitive levels. It helps improve the education in the real situation of the classroom. It shows that the class applied by mind tools regarded transitional students' cognitive levels and motive strategies increases students' biologies-learning achievements because it improves students' concentration and confidence efficiently connected with new knowledge by using visual effects. Also, it shows that transitional students' semantic network learning is superior to students' in formal operation stage and it is effective in forming learning contents in the structural organization with students' knowledge.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1195-1214
• /
• 2018

Typical search engines may not be the most efficient means of returning images in accordance with user requirements. With the help of semantic web technology, it is possible to search through images more precisely in any required domain, because the images are annotated according to a custom-built ontology. With appropriate annotations, a search can then, return images according to the context. This paper reports on the design of a tourism ontology relevant to touristic images. In particular, the image features and the meaning of the images are described using various properties, along with other types of information relevant to tourist attractions using the OWL language. The methodology used is described, commencing with building an image and tourism corpus, creating the ontology, and developing the search engine. The system was tested through a case study involving the western region of Thailand. The user can search specifying the specific class of image or they can use text-based searches. The results are ranked using weighted scores based on kinds of properties. The precision and recall of the prototype system was measured to show its efficiency. User satisfaction was also evaluated, was also performed and was found to be high.